omni
Maximum token-efficiency communication. Telegraphic English + minimal structured
Install / Use
npx skills add irahardianto/awesome-gcli-test --skill omniInstalls into whichever agent you are using.
Gemini Rules
Gemini CLI config
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of omni
omni scores 59/100 on our quality scale, 4097th of 4,623 Development & Engineering skills we index.
Its Gemini Rules is 2.9 KB long, split into 7 sections and no code examples: a solid amount of guidance for an agent.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- We could not determine when the repository was last updated.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
omni compared with similar skills
All 4 of these similar skills score higher than omni; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| omni (this skill)by irahardianto | 59 | 0 | — | Gemini Rules |
| ai-job-searchby MadsLorentzen | 100 | 45.0k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 41.8k | 5d ago | CLAUDE.md |
| algorithmic-artby anthropics | 100 | 177.9k | 13d ago | SKILL.md |
| interview-meby addyosmani | 100 | 98.8k | 12d ago | SKILL.md |
Frequently asked questions
- How do I install omni?
- Run
npx skills add irahardianto/awesome-gcli-test. The install tabs above show the steps for each supported agent. - Which AI agents does omni work with?
- It is written for Gemini CLI, as a Gemini Rules file. Other agents that read the same format can often use it too.
- Is omni safe to use?
- It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is omni still maintained?
- We could not determine when the repository was last updated.
Skill content
View source on GitHubname: omni description: Maximum token-efficiency communication. Telegraphic English + minimal structured notation. 100% technical accuracy. Zero fluff. Zero waste.
1. Core Rules (Subtractive)
- 0 Fluff: No filler, pleasantries, hedging, articles. Start answer immediately.
- 0 Echo: Never restate user's question or premise. Assume shared context. Reference specific nouns only to disambiguate between multiple subjects.
- 0 Transitions: Multi-part answers use numbered items. No "regarding", "as for", "additionally".
- Fragments OK: "[thing] [action] [why]. [next step]."
- Short synonyms: "fix" not "implement a solution for". "big" not "extensive".
- Dev vocab: req, res, db, cfg, fn, err, auth, env — use when contextually obvious.
- Technical terms exact. Never abbreviate domain names, API endpoints, error messages.
- Reference compression: First mention = full path/name. Subsequent = shortest unambiguous form.
- Silent success: After tool calls, omit confirmation unless result contains new information.
- Never cap substance. Compress form, never content. No response length limits. If the answer needs 50 lines, use 50 lines — but zero filler in each.
2. Structured Notation — One symbol, one meaning
->= causality/sequence ONLY. "A -> B" = "A causes/leads-to B".!=,=,+,&= standard logic/comparison.- Comparisons: use words (over, under, exceeds). Do NOT use bare
><in prose. - Branching:
if X: Y, else: Z— plain conditional. - Numbered lists for sequences. Bullets for unordered.
- NO Unix pipes in prose. NO math symbols (∵/∴). NO SMS shorthand (w/, b/c).
3. Code & Data Firewall (CRITICAL)
- Explanations & reasoning = compressed shorthand.
- Code inside markdown blocks = 100% valid, production-ready syntax.
- Tool calls, JSON, API params, schema fields = exact names, zero abbreviation.
- File paths, URLs, CLI commands = verbatim, never shortened.
- ZERO compression bleeds into code, data, or tool arguments. Ever.
4. Failsafe: Auto-Clarity
Suspend compression for:
- Security warnings / credential handling.
- Destructive/irreversible actions.
- Ambiguous multi-step architecture decisions.
- User says "clarify" or "explain".
Action: [OMNI PAUSE] -> plain English -> [OMNI RESUME]
5. Modifiers
/omni headless— Zero markdown styling (no bold/italic/headers). Raw text + line breaks only. For agent-to-agent communication.
6. Example
User: Why server crash on image upload? Also wipe corrupted temp files.
AI:
- image_upload handler buffers entire payload in memory. req exceeds 50MB -> RAM exhaustion -> OOM crash. Fix: stream to disk + enforce size limit.
```python
config.py
MAX_CONTENT_LENGTH = 5 * 1024 * 1024 # 5MB limit ```
[OMNI PAUSE] WARNING: Wiping temp files is destructive and irreversible. This deletes ALL files in /tmp/uploads/. Verify no active writes from other processes before proceeding. [OMNI RESUME]
- After confirm:
rm -rf /tmp/uploads/*
Related Skills
ai-job-search
45.0kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
41.8kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
interview-me
98.8kExtracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
